Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2581 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0467. Min Range: -10.0467
Max Act: 10.0467. Min Act: -0.1700
Data Index: 3948218 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0467. Min Range: -10.0467
Max Act: 9.7967. Min Act: -0.1700
Data Index: 1769463 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0467. Min Range: -10.0467
Max Act: 9.7967. Min Act: -0.1700
Data Index: 8272113 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0467. Min Range: -10.0467
Max Act: 9.7342. Min Act: -0.1700
Data Index: 2782454 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0467. Min Range: -10.0467
Max Act: 9.7342. Min Act: -0.1700
Data Index: 6314626 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0467. Min Range: -10.0467
Max Act: 9.6092. Min Act: -0.1700
Data Index: 6357855 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0467. Min Range: -10.0467
Max Act: 9.6092. Min Act: -0.1700
Data Index: 8298599 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0467. Min Range: -10.0467
Max Act: 9.6092. Min Act: -0.1700
Data Index: 8717044 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0467. Min Range: -10.0467
Max Act: 9.4842. Min Act: -0.1700
Data Index: 7578930 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0467. Min Range: -10.0467
Max Act: 9.4217. Min Act: -0.1700
Data Index: 440302 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0467. Min Range: -10.0467
Max Act: 9.4842. Min Act: -0.1700
Data Index: 858758 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0467. Min Range: -10.0467
Max Act: 9.4842. Min Act: -0.1700
Data Index: 6290333 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0467. Min Range: -10.0467
Max Act: 9.4217. Min Act: -0.1700
Data Index: 2125658 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0467. Min Range: -10.0467
Max Act: 9.4217. Min Act: -0.1700
Data Index: 1707234 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0467. Min Range: -10.0467
Max Act: 9.3592. Min Act: -0.1700
Data Index: 2201118 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0467. Min Range: -10.0467
Max Act: 9.3592. Min Act: -0.1700
Data Index: 5029768 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0467. Min Range: -10.0467
Max Act: 9.3592. Min Act: -0.1700
Data Index: 4087172 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0467. Min Range: -10.0467
Max Act: 9.3592. Min Act: -0.1700
Data Index: 7759491 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0467. Min Range: -10.0467
Max Act: 9.3592. Min Act: -0.1700
Data Index: 421554 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0467. Min Range: -10.0467
Max Act: 9.3592. Min Act: -0.1700
Data Index: 2652937 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19